LM Studio Logo

LM Studio Beta Releases

🪲 🗣️ Please report bugs and feedback to:

Beta and Experimental Releases

VersionBuildOSArchLast UpdatedDownload URL
0.3.59Windowsx86_642024-12-05LM-Studio-0.3.5-Setup.exe (x86)
0.3.59Macarm642024-12-05LM-Studio-0.3.5-arm64.dmg (Apple Silicon)
0.3.59Linuxx86_642024-12-05LM_Studio-0.3.5.AppImage (x86)
0.3.58Windowsarm642024-11-27LM-Studio-0.3.5-Setup.exe (ARM64)
LM Studio is provided under the terms of use.

Release Notes - LM Studio 0.3.5 Beta

Build 9

  • OpenAI-like tool calls now supports streaming! (!)
  • Improved tool call reliability through sampling configuration for both streaming and non-streaming tool use
  • Fixed lms load command
  • Fixed lms unload and lms status not working with embeddings
  • Fixed request logging when verbose logging is on (server)
  • Fixed some requests/responses are not redacted when logging prompts and responses are off
  • Fixed download resuming
  • Fixed more accessibility labels on UI elements
  • Fixed drag and drop file attachment not working
  • [MLX] Fixed bug which degraded performance for certain models

Build 8

  • RAG now works again
  • Fixed app not launching on some Linux distributions
  • Accessibility button label fixes (previously showing Object object)
  • Update llama.cpp to commit 46c69e0e (Support for OLMo 2)
  • MLX updates
    • Improved performance for MacOS 15
    • Improved performance for VLMs
    • Improved performance for long context generation
    • Bump mlx-engine versions: mlx==0.21.0, mlx_lm==0.20.1, mlx_vlm==0.1.1
    • Support for 3-bit and 6-bit quantization for MLX models

Build 7

  • Fixed a bug where models without chat templates, including embedding models, could not be indexed
  • Tool use docs are now up on: https://lmstudio.ai/docs/advanced/tool-use
  • Improved error reporting in the server API
  • Smoother model loader bar resizing on server page

Build 6

  • Passing an empty or null tools array in the API request is treated as no tools provided
  • Passing an empty or null tool_calls array in assistant messages in the API request is treated as the model making no cool calls

Build 5

  • Use any LLM that supports Tool Use and Function Calling through the OpenAI-like API
  • Qwen, Mistral, and Llama 3.1/3.2 models work well for tool use
  • New in-app "Quick Docs" with code snippets and tool use examples (top right corner)
  • Opens in a new window for side-by-side usage in LM Studio
  • New role tool in ChatHistoryData that represents the result of a tool call

Build 4

  • Fix for file attachments causing an error
  • Fix for long chat names pushing chat action buttons in the sidebar
  • Update llama.cpp engine: commit SHA ff252ea4

Build 3

  • Candidate fix for huggingface model search, download never reachable from within the app ("fetch failed")
  • Fix for pasting text from Microsoft Word giving an error about pasting an image
  • Fix for structured output for GGUF models lmstudio-bug-tracker/issues/173
  • Fix for machines with 1-2 CPU cores getting an error about CPU threads too low

Build 2

Stable release